(Update) Native Wan VACE Outpaint - Long Video Gen - Version 20250911 (Patreon)

Native Wan VACE Outpaint - Long Video Gen - Version 20250911

Update & Fixed:

Looping count and condition

Local Ollama Set as optional

Currently, I like to use FusionX Vace load as Lora model. It's more flexible for my setup, if you have FuxionX Vace as GGUF or Diff. Model, you can use yours and remove the FusionX Vace Lora.

Each 129 frames or 81 frames sampler frames should be follow the next segment of the whole video. It have not skip few frames or a part of video after Sampler Part 1 and start kick in to the Looping.

If you don't understand how to use it , check out the video above or this Tutorial Video : https://youtu.be/64gMlqxbgTk

Related Post : https://www.patreon.com/posts/134341201

Previous Version :

Ver.20250711 : https://www.patreon.com/posts/for-patreon-wan-133913160

Ver.20250719 : https://www.patreon.com/posts/update-native-134436685

Things you need to run this :

For Custom nodes

https://github.com/kijai/ComfyUI-WanVideoWrapper

https://github.com/kijai/ComfyUI-KJNodes

https://github.com/Fannovel16/comfyui_controlnet_aux

https://github.com/pythongosssss/ComfyUI-Custom-Scripts

https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite

https://github.com/chflame163/ComfyUI_LayerStyle

For Low VRAM GGUF

https://github.com/city96/ComfyUI-GGUF

https://github.com/neuratech-ai/ComfyUI-MultiGPU

Models

--Text Encoder--

(https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/text_encoders)

--VAE--

(https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/vae)

FusionX Wan VACE Model (Only for running with FusionX without lightx2v_cfg_step_distill_lora) :

Safetensors

https://huggingface.co/QuantStack/Wan2.1_T2V_14B_FusionX_VACE

GGUF

https://huggingface.co/QuantStack/Wan2.1-14B-T2V-FusionX-VACE-GGUF

Models (for running without FusionX-CausVid )

Wan2.1_vace

(https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/diffusion_models)

Or

Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE-GGUF

(https://huggingface.co/QuantStack/Wan2.1_T2V_14B_LightX2V_StepCfgDistill_VACE-GGUF)

Wan21_T2V_14B_MoviiGen_lora_rank32_fp16

(https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan21_T2V_14B_MoviiGen_lora_rank32_fp16.safetensors)

Wan21_T2V_14B_lightx2v_cfg_step_distill_lora_rank32

(https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan21_T2V_14B_lightx2v_cfg_step_distill_lora_rank32.safetensors)

Wan2.1-Fun-14B-InP-MPS

(https://huggingface.co/alibaba-pai/Wan2.1-Fun-Reward-LoRAs/blob/main/Wan2.1-Fun-14B-InP-MPS.safetensors)

DetailEnhancerV1.safetensors

(https://huggingface.co/vrgamedevgirl84/Wan14BT2VFusioniX/tree/main/OtherLoRa's)